Uncensored chat gpt API Documentation

Authentication and Keys

Start by generating a key on the dashboard. Sign in with Google or an email password to see the token immediately. No phone number is required. The base URL for all requests is https://api.gptunhinged.com/v1. Use this URL and your key in your client configuration.

Each account holds one active key. Requesting a new key replaces the old one instantly. Your prompts are not used for training. The key authenticates your prepaid credit usage.

Chat Completions Endpoint

Send messages to POST /v1/chat/completions. The model id is uncensored. The API returns text responses for your application logic.

Copycurl https://api.gptunhinged.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return the ascii art for a skull"}]
  }'

Requests must stay under 8 MB. The model accepts standard message structures. You can send system prompts to define behavior. The context window allows 100,000 tokens total. This includes your input and the generated output combined.

Python SDK Integration

Use the official Python library to connect easily. Change the base URL to point to our servers. The rest of the code remains compatible with standard implementations.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.gptunhinged.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

This approach works for most Python projects. You can pass parameters like temperature directly. The client handles the HTTP requests for you. Ensure your key is stored securely in your environment variables.

Node SDK Integration

Integrate the Node SDK by updating the base URL. The package accepts the same parameters as the standard OpenAI client. This keeps your code portable.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.gptunhinged.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Configure the API key in the client initialization. The uncensored model responds to your prompts. You can use standard message arrays. The library handles serialization automatically.

Streaming Responses

Enable streaming by setting stream: true. The API returns data chunks as they are generated. This reduces perceived latency for end-users.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Token usage details appear in the final chunk. You can process each token as it arrives. This is useful for real-time displays. The SSE format ensures reliable delivery. Buffer the chunks if your UI requires complete sentences.

Limits, Errors, and Context

Watch your rate limits and credit balance. You get 300 requests per minute per key. Only eight requests run simultaneously. The 429 error indicates you hit this limit. A 401 error means your key is invalid. A 402 error signals insufficient credit.

Errors are free. Your prepaid credit never expires. The context window holds 100,000 tokens. Max output is 16,000 tokens per request. Set max_tokens to control length.